Hi Stefan,

1 - I just contacted Eyal Ofek from Microsoft Research, one of the authors of that SWT paper.

My mail :

I am Abid K, a graduate student from India. I have some questions regarding your paper "Detecting Text in Natural Scenes with Stroke Width Transform".

1 - Is it patented?
2 - Can I implement it myself and contribute it to some Open Source image processing libraries like scikit-image, OpenCV etc?

Reply from Eyal

1.       Yes it is patented.
2.       I believe there are implementations of SWT or a derivative out there.

And on asking more details on second question, he replied:
Your quest6ion is legal, and I cannot answer that – I’ll send it to the people that deals with patents.

2 - Regarding SIMD optimization : Is there any particular reason for less number of SIMD optimized functions? Other libraries seems to spend a lot of time on this.

Regards

Abid K.


On Tue, Feb 18, 2014 at 9:34 PM, Stéfan van der Walt <stefan@sun.ac.za> wrote:
On Tue, Feb 18, 2014 at 5:53 PM, abid rahman <abidrahman2@gmail.com> wrote:
> So I think SWT is patented, isn't it?

I'm not sure--I would like to contact the researchers in Microsoft to
get clarity (or perhaps someone would volunteer to do so?)

> I wonder if implementation of this paper is considered to be a GSoC project,
> I would like to work on it.

I think so--the goal is text detection, not to implement any specific
algorithm (I updated the project description to include this paper).

> Another question : What is the status of SIMD optimization in scikit-image?
> Does Cython support such kind of optimization works? Is there any SIMD
> optimized functions available in scikit-image?

These are the only vectorized ops we have:

https://github.com/scikit-image/scikit-image/blob/master/skimage/_shared/vectorized_ops.h

Stéfan

--
You received this message because you are subscribed to the Google Groups "scikit-image" group.
To unsubscribe from this group and stop receiving emails from it, send an email to scikit-image+unsubscribe@googlegroups.com.
For more options, visit https://groups.google.com/groups/opt_out.